entangledstate-isbn 1.4.0 → 1.4.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README +1 -1
- data/Rakefile +0 -18
- data/VERSION +1 -0
- data/isbn.gemspec +290 -7
- data/lib/isbn.rb +6 -6
- data/src/gocr-0.48/.cvsignore +6 -0
- data/src/gocr-0.48/AUTHORS +7 -0
- data/src/gocr-0.48/BUGS +55 -0
- data/src/gocr-0.48/CREDITS +17 -0
- data/src/gocr-0.48/HISTORY +243 -0
- data/src/gocr-0.48/INSTALL +83 -0
- data/src/gocr-0.48/Makefile +193 -0
- data/src/gocr-0.48/Makefile.in +193 -0
- data/src/gocr-0.48/README +165 -0
- data/src/gocr-0.48/READMEde.txt +80 -0
- data/src/gocr-0.48/REMARK.txt +18 -0
- data/src/gocr-0.48/REVIEW +538 -0
- data/src/gocr-0.48/TODO +65 -0
- data/src/gocr-0.48/bin/.cvsignore +2 -0
- data/src/gocr-0.48/bin/create_db +38 -0
- data/src/gocr-0.48/bin/gocr.tcl +527 -0
- data/src/gocr-0.48/bin/gocr_chk.sh +44 -0
- data/src/gocr-0.48/configure +4689 -0
- data/src/gocr-0.48/configure.in +71 -0
- data/src/gocr-0.48/doc/.#Makefile.1.6 +39 -0
- data/src/gocr-0.48/doc/.cvsignore +2 -0
- data/src/gocr-0.48/doc/Makefile +39 -0
- data/src/gocr-0.48/doc/Makefile.in +39 -0
- data/src/gocr-0.48/doc/example.dtd +53 -0
- data/src/gocr-0.48/doc/example.xml +21 -0
- data/src/gocr-0.48/doc/examples.txt +67 -0
- data/src/gocr-0.48/doc/gocr.html +578 -0
- data/src/gocr-0.48/doc/unicode.txt +57 -0
- data/src/gocr-0.48/examples/.#Makefile.1.22 +166 -0
- data/src/gocr-0.48/examples/4x6.png +0 -0
- data/src/gocr-0.48/examples/4x6.txt +2 -0
- data/src/gocr-0.48/examples/5x7.png +0 -0
- data/src/gocr-0.48/examples/5x7.png.txt +2 -0
- data/src/gocr-0.48/examples/5x8.png +0 -0
- data/src/gocr-0.48/examples/5x8.png.txt +2 -0
- data/src/gocr-0.48/examples/Makefile +166 -0
- data/src/gocr-0.48/examples/color.fig +20 -0
- data/src/gocr-0.48/examples/ex.fig +16 -0
- data/src/gocr-0.48/examples/font.tex +22 -0
- data/src/gocr-0.48/examples/font1.tex +46 -0
- data/src/gocr-0.48/examples/font2.fig +27 -0
- data/src/gocr-0.48/examples/font_nw.tex +24 -0
- data/src/gocr-0.48/examples/handwrt1.jpg +0 -0
- data/src/gocr-0.48/examples/handwrt1.txt +10 -0
- data/src/gocr-0.48/examples/inverse.fig +20 -0
- data/src/gocr-0.48/examples/matrix.jpg +0 -0
- data/src/gocr-0.48/examples/ocr-a-subset.png +0 -0
- data/src/gocr-0.48/examples/ocr-a-subset.png.txt +4 -0
- data/src/gocr-0.48/examples/ocr-a.png +0 -0
- data/src/gocr-0.48/examples/ocr-a.txt +6 -0
- data/src/gocr-0.48/examples/ocr-b.png +0 -0
- data/src/gocr-0.48/examples/ocr-b.png.txt +4 -0
- data/src/gocr-0.48/examples/polish.tex +28 -0
- data/src/gocr-0.48/examples/rotate45.fig +14 -0
- data/src/gocr-0.48/examples/score +36 -0
- data/src/gocr-0.48/examples/text.tex +28 -0
- data/src/gocr-0.48/gocr.spec +143 -0
- data/src/gocr-0.48/gpl.html +537 -0
- data/src/gocr-0.48/include/.cvsignore +2 -0
- data/src/gocr-0.48/include/config.h +36 -0
- data/src/gocr-0.48/include/config.h.in +36 -0
- data/src/gocr-0.48/include/version.h +2 -0
- data/src/gocr-0.48/install-sh +3 -0
- data/src/gocr-0.48/make.bat +57 -0
- data/src/gocr-0.48/man/.cvsignore +2 -0
- data/src/gocr-0.48/man/Makefile +29 -0
- data/src/gocr-0.48/man/Makefile.in +29 -0
- data/src/gocr-0.48/man/man1/gocr.1 +166 -0
- data/src/gocr-0.48/src/.cvsignore +4 -0
- data/src/gocr-0.48/src/Makefile +132 -0
- data/src/gocr-0.48/src/Makefile.in +132 -0
- data/src/gocr-0.48/src/amiga.h +31 -0
- data/src/gocr-0.48/src/barcode.c +846 -0
- data/src/gocr-0.48/src/barcode.c.orig +593 -0
- data/src/gocr-0.48/src/barcode.h +11 -0
- data/src/gocr-0.48/src/box.c +372 -0
- data/src/gocr-0.48/src/database.c +462 -0
- data/src/gocr-0.48/src/detect.c +943 -0
- data/src/gocr-0.48/src/gocr.c +373 -0
- data/src/gocr-0.48/src/gocr.h +288 -0
- data/src/gocr-0.48/src/jconv.c +168 -0
- data/src/gocr-0.48/src/job.c +84 -0
- data/src/gocr-0.48/src/lines.c +350 -0
- data/src/gocr-0.48/src/list.c +334 -0
- data/src/gocr-0.48/src/list.h +90 -0
- data/src/gocr-0.48/src/ocr0.c +6756 -0
- data/src/gocr-0.48/src/ocr0.h +63 -0
- data/src/gocr-0.48/src/ocr0n.c +1475 -0
- data/src/gocr-0.48/src/ocr1.c +85 -0
- data/src/gocr-0.48/src/ocr1.h +3 -0
- data/src/gocr-0.48/src/otsu.c +289 -0
- data/src/gocr-0.48/src/otsu.h +23 -0
- data/src/gocr-0.48/src/output.c +289 -0
- data/src/gocr-0.48/src/output.h +37 -0
- data/src/gocr-0.48/src/pcx.c +153 -0
- data/src/gocr-0.48/src/pcx.h +9 -0
- data/src/gocr-0.48/src/pgm2asc.c +2893 -0
- data/src/gocr-0.48/src/pgm2asc.h +105 -0
- data/src/gocr-0.48/src/pixel.c +537 -0
- data/src/gocr-0.48/src/pnm.c +533 -0
- data/src/gocr-0.48/src/pnm.h +35 -0
- data/src/gocr-0.48/src/progress.c +87 -0
- data/src/gocr-0.48/src/progress.h +42 -0
- data/src/gocr-0.48/src/remove.c +703 -0
- data/src/gocr-0.48/src/tga.c +87 -0
- data/src/gocr-0.48/src/tga.h +6 -0
- data/src/gocr-0.48/src/unicode.c +1314 -0
- data/src/gocr-0.48/src/unicode.h +1257 -0
- data/src/jpeg-7/Makefile.am +133 -0
- data/src/jpeg-7/Makefile.in +1089 -0
- data/src/jpeg-7/README +322 -0
- data/src/jpeg-7/aclocal.m4 +8990 -0
- data/src/jpeg-7/ansi2knr.1 +36 -0
- data/src/jpeg-7/ansi2knr.c +739 -0
- data/src/jpeg-7/cderror.h +132 -0
- data/src/jpeg-7/cdjpeg.c +181 -0
- data/src/jpeg-7/cdjpeg.h +187 -0
- data/src/jpeg-7/change.log +270 -0
- data/src/jpeg-7/cjpeg.1 +325 -0
- data/src/jpeg-7/cjpeg.c +616 -0
- data/src/jpeg-7/ckconfig.c +402 -0
- data/src/jpeg-7/coderules.txt +118 -0
- data/src/jpeg-7/config.guess +1561 -0
- data/src/jpeg-7/config.sub +1686 -0
- data/src/jpeg-7/configure +17139 -0
- data/src/jpeg-7/configure.ac +317 -0
- data/src/jpeg-7/depcomp +630 -0
- data/src/jpeg-7/djpeg.1 +251 -0
- data/src/jpeg-7/djpeg.c +617 -0
- data/src/jpeg-7/example.c +433 -0
- data/src/jpeg-7/filelist.txt +215 -0
- data/src/jpeg-7/install-sh +520 -0
- data/src/jpeg-7/install.txt +1097 -0
- data/src/jpeg-7/jaricom.c +148 -0
- data/src/jpeg-7/jcapimin.c +282 -0
- data/src/jpeg-7/jcapistd.c +161 -0
- data/src/jpeg-7/jcarith.c +921 -0
- data/src/jpeg-7/jccoefct.c +453 -0
- data/src/jpeg-7/jccolor.c +459 -0
- data/src/jpeg-7/jcdctmgr.c +482 -0
- data/src/jpeg-7/jchuff.c +1612 -0
- data/src/jpeg-7/jcinit.c +65 -0
- data/src/jpeg-7/jcmainct.c +293 -0
- data/src/jpeg-7/jcmarker.c +667 -0
- data/src/jpeg-7/jcmaster.c +770 -0
- data/src/jpeg-7/jcomapi.c +106 -0
- data/src/jpeg-7/jconfig.bcc +48 -0
- data/src/jpeg-7/jconfig.cfg +45 -0
- data/src/jpeg-7/jconfig.dj +38 -0
- data/src/jpeg-7/jconfig.mac +43 -0
- data/src/jpeg-7/jconfig.manx +43 -0
- data/src/jpeg-7/jconfig.mc6 +52 -0
- data/src/jpeg-7/jconfig.sas +43 -0
- data/src/jpeg-7/jconfig.st +42 -0
- data/src/jpeg-7/jconfig.txt +155 -0
- data/src/jpeg-7/jconfig.vc +45 -0
- data/src/jpeg-7/jconfig.vms +37 -0
- data/src/jpeg-7/jconfig.wat +38 -0
- data/src/jpeg-7/jcparam.c +632 -0
- data/src/jpeg-7/jcprepct.c +358 -0
- data/src/jpeg-7/jcsample.c +545 -0
- data/src/jpeg-7/jctrans.c +381 -0
- data/src/jpeg-7/jdapimin.c +396 -0
- data/src/jpeg-7/jdapistd.c +275 -0
- data/src/jpeg-7/jdarith.c +762 -0
- data/src/jpeg-7/jdatadst.c +151 -0
- data/src/jpeg-7/jdatasrc.c +212 -0
- data/src/jpeg-7/jdcoefct.c +736 -0
- data/src/jpeg-7/jdcolor.c +396 -0
- data/src/jpeg-7/jdct.h +393 -0
- data/src/jpeg-7/jddctmgr.c +382 -0
- data/src/jpeg-7/jdhuff.c +1309 -0
- data/src/jpeg-7/jdinput.c +384 -0
- data/src/jpeg-7/jdmainct.c +512 -0
- data/src/jpeg-7/jdmarker.c +1360 -0
- data/src/jpeg-7/jdmaster.c +663 -0
- data/src/jpeg-7/jdmerge.c +400 -0
- data/src/jpeg-7/jdpostct.c +290 -0
- data/src/jpeg-7/jdsample.c +361 -0
- data/src/jpeg-7/jdtrans.c +136 -0
- data/src/jpeg-7/jerror.c +252 -0
- data/src/jpeg-7/jerror.h +304 -0
- data/src/jpeg-7/jfdctflt.c +174 -0
- data/src/jpeg-7/jfdctfst.c +230 -0
- data/src/jpeg-7/jfdctint.c +4348 -0
- data/src/jpeg-7/jidctflt.c +242 -0
- data/src/jpeg-7/jidctfst.c +368 -0
- data/src/jpeg-7/jidctint.c +5137 -0
- data/src/jpeg-7/jinclude.h +91 -0
- data/src/jpeg-7/jmemansi.c +167 -0
- data/src/jpeg-7/jmemdos.c +638 -0
- data/src/jpeg-7/jmemdosa.asm +379 -0
- data/src/jpeg-7/jmemmac.c +289 -0
- data/src/jpeg-7/jmemmgr.c +1118 -0
- data/src/jpeg-7/jmemname.c +276 -0
- data/src/jpeg-7/jmemnobs.c +109 -0
- data/src/jpeg-7/jmemsys.h +198 -0
- data/src/jpeg-7/jmorecfg.h +369 -0
- data/src/jpeg-7/jpegint.h +395 -0
- data/src/jpeg-7/jpeglib.h +1135 -0
- data/src/jpeg-7/jpegtran.1 +272 -0
- data/src/jpeg-7/jpegtran.c +546 -0
- data/src/jpeg-7/jquant1.c +856 -0
- data/src/jpeg-7/jquant2.c +1310 -0
- data/src/jpeg-7/jutils.c +179 -0
- data/src/jpeg-7/jversion.h +14 -0
- data/src/jpeg-7/libjpeg.map +4 -0
- data/src/jpeg-7/libjpeg.txt +3067 -0
- data/src/jpeg-7/ltmain.sh +8406 -0
- data/src/jpeg-7/makcjpeg.st +36 -0
- data/src/jpeg-7/makdjpeg.st +36 -0
- data/src/jpeg-7/makeadsw.vc6 +77 -0
- data/src/jpeg-7/makeasln.vc9 +33 -0
- data/src/jpeg-7/makecdep.vc6 +82 -0
- data/src/jpeg-7/makecdsp.vc6 +130 -0
- data/src/jpeg-7/makecmak.vc6 +159 -0
- data/src/jpeg-7/makecvcp.vc9 +186 -0
- data/src/jpeg-7/makeddep.vc6 +82 -0
- data/src/jpeg-7/makeddsp.vc6 +130 -0
- data/src/jpeg-7/makedmak.vc6 +159 -0
- data/src/jpeg-7/makedvcp.vc9 +186 -0
- data/src/jpeg-7/makefile.ansi +220 -0
- data/src/jpeg-7/makefile.bcc +291 -0
- data/src/jpeg-7/makefile.dj +226 -0
- data/src/jpeg-7/makefile.manx +220 -0
- data/src/jpeg-7/makefile.mc6 +255 -0
- data/src/jpeg-7/makefile.mms +224 -0
- data/src/jpeg-7/makefile.sas +258 -0
- data/src/jpeg-7/makefile.unix +234 -0
- data/src/jpeg-7/makefile.vc +217 -0
- data/src/jpeg-7/makefile.vms +142 -0
- data/src/jpeg-7/makefile.wat +239 -0
- data/src/jpeg-7/makejdep.vc6 +423 -0
- data/src/jpeg-7/makejdsp.vc6 +285 -0
- data/src/jpeg-7/makejdsw.vc6 +29 -0
- data/src/jpeg-7/makejmak.vc6 +425 -0
- data/src/jpeg-7/makejsln.vc9 +17 -0
- data/src/jpeg-7/makejvcp.vc9 +328 -0
- data/src/jpeg-7/makeproj.mac +213 -0
- data/src/jpeg-7/makerdep.vc6 +6 -0
- data/src/jpeg-7/makerdsp.vc6 +78 -0
- data/src/jpeg-7/makermak.vc6 +110 -0
- data/src/jpeg-7/makervcp.vc9 +133 -0
- data/src/jpeg-7/maketdep.vc6 +43 -0
- data/src/jpeg-7/maketdsp.vc6 +122 -0
- data/src/jpeg-7/maketmak.vc6 +131 -0
- data/src/jpeg-7/maketvcp.vc9 +178 -0
- data/src/jpeg-7/makewdep.vc6 +6 -0
- data/src/jpeg-7/makewdsp.vc6 +78 -0
- data/src/jpeg-7/makewmak.vc6 +110 -0
- data/src/jpeg-7/makewvcp.vc9 +133 -0
- data/src/jpeg-7/makljpeg.st +68 -0
- data/src/jpeg-7/maktjpeg.st +30 -0
- data/src/jpeg-7/makvms.opt +4 -0
- data/src/jpeg-7/missing +376 -0
- data/src/jpeg-7/rdbmp.c +439 -0
- data/src/jpeg-7/rdcolmap.c +253 -0
- data/src/jpeg-7/rdgif.c +38 -0
- data/src/jpeg-7/rdjpgcom.1 +63 -0
- data/src/jpeg-7/rdjpgcom.c +515 -0
- data/src/jpeg-7/rdppm.c +459 -0
- data/src/jpeg-7/rdrle.c +387 -0
- data/src/jpeg-7/rdswitch.c +365 -0
- data/src/jpeg-7/rdtarga.c +500 -0
- data/src/jpeg-7/structure.txt +945 -0
- data/src/jpeg-7/testimg.bmp +0 -0
- data/src/jpeg-7/testimg.jpg +0 -0
- data/src/jpeg-7/testimg.ppm +4 -0
- data/src/jpeg-7/testimgp.jpg +0 -0
- data/src/jpeg-7/testorig.jpg +0 -0
- data/src/jpeg-7/testprog.jpg +0 -0
- data/src/jpeg-7/transupp.c +1533 -0
- data/src/jpeg-7/transupp.h +205 -0
- data/src/jpeg-7/usage.txt +605 -0
- data/src/jpeg-7/wizard.txt +211 -0
- data/src/jpeg-7/wrbmp.c +442 -0
- data/src/jpeg-7/wrgif.c +399 -0
- data/src/jpeg-7/wrjpgcom.1 +103 -0
- data/src/jpeg-7/wrjpgcom.c +583 -0
- data/src/jpeg-7/wrppm.c +269 -0
- data/src/jpeg-7/wrrle.c +305 -0
- data/src/jpeg-7/wrtarga.c +253 -0
- metadata +287 -6
- data/LICENSE +0 -20
- data/VERSION.yml +0 -4
@@ -0,0 +1,538 @@
|
|
1
|
+
This is a list of reviews, so that developers don't get confused with the new
|
2
|
+
changes. Please document what you do here.
|
3
|
+
|
4
|
+
() done
|
5
|
+
[] done, but should be reviewed
|
6
|
+
|| to be done, do if you can
|
7
|
+
?? question: if you know, solve it
|
8
|
+
Writer: put your initials inside.
|
9
|
+
|
10
|
+
5/8
|
11
|
+
(bbg) changed box1 to head_data.
|
12
|
+
(bbg) changed boxd to head_db.
|
13
|
+
|bbg| box2 static variables do not exist anymore. They were confusing,
|
14
|
+
since these names were used as arguments to functions too. From what I've
|
15
|
+
seen, this will not affect the program.
|
16
|
+
(js) agree
|
17
|
+
(bbg) added new file: box.c, with all the functions that deal with boxes.
|
18
|
+
(bbg) added new file: database.c, with all the functions that deal with db.
|
19
|
+
[bbg] ocr_db()
|
20
|
+
|bbg| split pgm2asc(): the function would still exist, but call other
|
21
|
+
subfunctions which are part of it now. I suggest:
|
22
|
+
- find_letters()
|
23
|
+
- remove_dust()
|
24
|
+
- remove_pictures()
|
25
|
+
- remove_melted_serifs()
|
26
|
+
- find_longest_line()
|
27
|
+
- detect_lines()
|
28
|
+
etc: they are practically already defined between {}.
|
29
|
+
?bbg? pgm2asc: it has 2 frame letter codes, 2 find pictures, 2 remove
|
30
|
+
dust
|
31
|
+
|js| It is result of last (not finished) big rewriting of code
|
32
|
+
will be changed later
|
33
|
+
|bbg| vvv (or equivalent) should be global.
|
34
|
+
|
35
|
+
6/8
|
36
|
+
(bbg) general linked lists done (list.*).
|
37
|
+
|bbg| Functions in box.c should be changed by the new general ones.
|
38
|
+
linearr should too.
|
39
|
+
(bbg) strc() and in_str() changed by strchr.
|
40
|
+
?bbg? shouldn't test_umlaut() belong to another file, like ocr0.cc?
|
41
|
+
js: good idea
|
42
|
+
(bbg) moved to ocr0.cc
|
43
|
+
?bbg? there are several functions with 2 or 3 versions (detect_lines,
|
44
|
+
detect_lines2, for example). Do they do the same thing (and one
|
45
|
+
is older) or different things?
|
46
|
+
js: different, they are different childs from same mother
|
47
|
+
they are going more different in future
|
48
|
+
?bbg? What do ini_list(), excude() and getresult() do? They don't seem
|
49
|
+
to be used. If they are useless, please delete them.
|
50
|
+
js: read the new comments in the file (should be in seperate file?)
|
51
|
+
|bbg| document pixel().
|
52
|
+
:done.
|
53
|
+
|bbg| Many, many commented lines all over the file; should be cleaned.
|
54
|
+
:done.
|
55
|
+
|bbg| Change new->malloc, delete->free.
|
56
|
+
:done
|
57
|
+
|
58
|
+
7/8
|
59
|
+
(js) some comments added in pgm2asc.cc
|
60
|
+
|bbg| instead of p.p[x+y*p.x], use the new macro pixel_at(p, x, y).
|
61
|
+
Not all substitutions done yet.
|
62
|
+
:done.
|
63
|
+
(bbg) excude() renamed to exclude().
|
64
|
+
?bbg? what are the pixel bits meaning? A table would be useful.
|
65
|
+
(js) not stable: lowest (3-4?) bits are for temporary use
|
66
|
+
highest (4?) bits are for intensity
|
67
|
+
|bbg| must change all "type &p" arguments.
|
68
|
+
:done
|
69
|
+
|bbg| should make argument order standard: at the present, sometimes the
|
70
|
+
order is x0,x1,y0,y1, sometimes x0,y0,x1,y1, pix is not always the
|
71
|
+
first, etc.
|
72
|
+
(bbg) turmite(): changed for+if -> while. Is is correct? I think so, but
|
73
|
+
a test wouldn't hurt. Also optimized the function.
|
74
|
+
(js) I test it after complete review.
|
75
|
+
|
76
|
+
8/8
|
77
|
+
(js) pgm2asc.cc: generally pix *p used, pgm2asc() partly rewritten
|
78
|
+
|js| ocr0.cc: pix *p must be used everywhere
|
79
|
+
:done
|
80
|
+
(bbg) pixel(): first part (c33 filling) optimized.
|
81
|
+
(bbg) minor optimizations, cut superflous counters.
|
82
|
+
?bbg? copybox: shouldn't b->p be free()d, or realloc()ed? There's also a new
|
83
|
+
faster version (using memcpy), but there's no unmarking of pixels; I'm
|
84
|
+
also not sure if they are equivalent, since I'm not calling pixel. It's
|
85
|
+
between #ifs.
|
86
|
+
|
87
|
+
9/8
|
88
|
+
(bbg) Started to change linearr to linked lists; linearr is obsolete now,
|
89
|
+
and textlines too.
|
90
|
+
(bbg) free_textlines() and getTextLine() use linked lists (instead of linearr)
|
91
|
+
now. The first may be deleted in the future.
|
92
|
+
[bbg] store_boxtree_textlines use linked lists (instead of linearr) now, but
|
93
|
+
should be tested and reviewed; specially if (box2->c == ' ') since it
|
94
|
+
doesn't check for an \n anymore (why should it?). Also the extra list_app
|
95
|
+
should be checked. Check too if "if (!(mo & 8))" shouldn't come before
|
96
|
+
"if (box2->c != '_')".
|
97
|
+
:done
|
98
|
+
(bbg) Moved copybox() to box.c
|
99
|
+
?bbg? put(): What are ia and io?
|
100
|
+
js: ia int_and, io int_or new_pixel=(old_pixel & ia) | io
|
101
|
+
for more praktical use
|
102
|
+
|bbg| What about putting remove_dust, remove_picture, remove_etc in another
|
103
|
+
file, such as clean.c or remove.c?
|
104
|
+
js: should be made
|
105
|
+
bbg: done
|
106
|
+
|bbg| several #ifdef's pending approval or review. Get rid of them.
|
107
|
+
:done
|
108
|
+
[bbg] Added code to open pgm files using libpgm. Not tested, but should be OK.
|
109
|
+
[bbg] started to write writepbm, writeppm.
|
110
|
+
|
111
|
+
10/8
|
112
|
+
[js] pgm2asc() new functions created
|
113
|
+
(bbg) moved remove_* functions to remove.c
|
114
|
+
(bbg) added doc/ directory; moved ocr.tex to doc/; created examples.txt.
|
115
|
+
(bbg) added UNICODE support: unicode.h contains all symbols we will ever need,
|
116
|
+
unicode.c contains two conversion functions.
|
117
|
+
(bbg) most of Unicode->TeX convert() (0x7F-0xFF) codes are done.
|
118
|
+
[bbg] several compose() codes done.
|
119
|
+
|
120
|
+
11/8
|
121
|
+
(bbg) new pnm IO functions, much better now.
|
122
|
+
[bbg] fixed part of ocr0.cc: since arguments changed from pix &p to pix *p, it
|
123
|
+
wasn't compiling. Must fix the pix b; should it be changed to pix *b?
|
124
|
+
:done
|
125
|
+
|bbg| Use new Unicode code; change all old code using unsigned char to wchar_t.
|
126
|
+
Work started. Take care: old libc functions won't work anymore. Use those
|
127
|
+
defined in <wchar.h>. Perhaps we should wait until the review is done and
|
128
|
+
gocr is working again.
|
129
|
+
:do it in 0.3.1 only.
|
130
|
+
?bbg? should we move wert code to a new file?
|
131
|
+
(js) we should
|
132
|
+
?bbg? should we move all code a /src sudirectory?
|
133
|
+
(js) we should, same step should rename .cc to .c
|
134
|
+
|bbg| fix Makefile (or better, configure.in) to reflect new files.
|
135
|
+
:done
|
136
|
+
[bbg] started to change all the for(box=head_data) to for_each_data. CAREFUL:
|
137
|
+
you cannot use for_each_data recursively. On the next layer, you must use
|
138
|
+
something like for(box=list_get_header; box; box=list_next(box));
|
139
|
+
:done
|
140
|
+
|
141
|
+
13/8
|
142
|
+
(bbg) finished changing for(box=head_data). Old box_* functions still used,
|
143
|
+
must fix.
|
144
|
+
(bbg) cleaned 99% of the warning/errors when compiling pgm2asc.cc
|
145
|
+
[bbg] fix: warning: control reaches end of non-void function
|
146
|
+
`compare_unknown_with_known_chars(pix *, int)'
|
147
|
+
:done
|
148
|
+
[bbg] check if pgm2asc.cc:474:i = ((pixel(p, x, y) < cs) ? 0 : 1); is useless
|
149
|
+
or not.
|
150
|
+
(js) useless, relict from older review-changes
|
151
|
+
(bbg) vvv is now part of struct environment.
|
152
|
+
(bbg) removed Uchar, may conflict with other libs. Use unsigned char.
|
153
|
+
|
154
|
+
15/8
|
155
|
+
(bbg) Tim Waugh sent man page; added him in the thanks of README.txt
|
156
|
+
[bbg] should break README.txt in: INSTALL, CREDITS, TODO, HISTORY.
|
157
|
+
:done
|
158
|
+
(bbg) more changes from box_* to list_*
|
159
|
+
|
160
|
+
16/8
|
161
|
+
(bbg) added greek letters to the unicode.c functions. Not complete.
|
162
|
+
(bbg) added punctuation symbols to the unicode.c functions. Not complete.
|
163
|
+
(bbg) added ISO8859-1 support to the unicode.c functions. 0x20-0xFF supported,
|
164
|
+
ligatures supported.
|
165
|
+
|
166
|
+
18/8
|
167
|
+
[bbg] fix try_to_divide_boxes to the new general linked list.
|
168
|
+
[bbg] most for_each_data have a line like box2 = list_get_current, which is
|
169
|
+
unnecessary. Change box2 by list_get_current. To avoid clumsiness, it
|
170
|
+
maybe a good idea to create a new #define lgc(a) list_get_current(a).
|
171
|
+
|
172
|
+
25/8
|
173
|
+
(js) ./src created, .cc,.h,.c moved to src, .cc renamed to .c
|
174
|
+
[js] try to get make working (make jconv) see config.h: USE_LIBPNM => HAVE_PNM_H
|
175
|
+
|js| list.c L66 data_before ??? what does that mean?
|
176
|
+
(bbg) mistyped, fixed.
|
177
|
+
list_del should be tested
|
178
|
+
:done
|
179
|
+
?js? unicode.c there are undefined DEFS L89++ (i have put it in /* */)
|
180
|
+
L150++,L185++,L633++
|
181
|
+
(bbg) fixed
|
182
|
+
[js] make works again (now you can make compilation tests on changes)
|
183
|
+
... but SEGFAULT
|
184
|
+
|
185
|
+
26/8
|
186
|
+
(bbg) fixed casting warnings in unicode.c; fixed undefined DEFS.
|
187
|
+
|bbg| fix the missing LaTeX codes in unicode.c.
|
188
|
+
|
189
|
+
28/8
|
190
|
+
?js? configure does not find /usr/X11R6/include/pnm.h, why?
|
191
|
+
[js] fixed some bugs to get gocr working, but there are still big bugs
|
192
|
+
|
193
|
+
30/8
|
194
|
+
(bbg) fixed all gcc warnings. Some bugs killed in the process.
|
195
|
+
(bbg) fixed pnm.c compilation problem
|
196
|
+
|bbg| have to fix database.c:102
|
197
|
+
|bbg| MANDATORY: change all old linked list code to the new one. This means:
|
198
|
+
get rid of box_* functions, the header->data stuff, etc. The new linked
|
199
|
+
list code is probably working 100%.
|
200
|
+
(bbg) changed $(CXX) to $(CC). C conversion completed!
|
201
|
+
(bbg) added jconv and gocr sections to src/Makefile.
|
202
|
+
(bbg) new ISO8859-1 codes in unicode.c:convert.
|
203
|
+
(bbg) fixed several bugs in list.c, and patched list_del() to return 2 if
|
204
|
+
deleted data was list->current.
|
205
|
+
|
206
|
+
1/9
|
207
|
+
(bbg) added new list_init(). Use it.
|
208
|
+
(bbg) wrote a fix to the list_del()+for_each_data bug. It's not very good, but
|
209
|
+
works. Fixes the nested loops too. Now you can use for_each_data
|
210
|
+
recursively.
|
211
|
+
|
212
|
+
8/9
|
213
|
+
(bbg) more fixes from the old LL system to the new one.
|
214
|
+
(js) added list_higher_level(), fix list_lower_level()
|
215
|
+
bug fixed free_textlines(),store_boxtree_lines(),store_boxtree_lines()
|
216
|
+
(js) review of pgm2asc() finished
|
217
|
+
|
218
|
+
9/9
|
219
|
+
(bbg) more fixes from the old LL system to the new one.
|
220
|
+
(bbg) fixed the realloc fixes of 8/9 in fix list_lower_level(),
|
221
|
+
free_textlines(),store_boxtree_lines(), and fixed list_higher_level(),
|
222
|
+
to avoid a blow if realloc fails. Now things continue working.
|
223
|
+
(js) compilation bug removed
|
224
|
+
(bbg) reviewed context_correction().
|
225
|
+
(bbg) moved output_list() and write_img() to output.c. Added output.h.
|
226
|
+
?bbg? Since output.c functions are only for debugging, what do you think about
|
227
|
+
adding some #ifdef DEBUGs to make a smaller, faster code? It doesn't have
|
228
|
+
to be done now, but it's an idea.
|
229
|
+
(js) its general good idea, but I would use a DEBUG level
|
230
|
+
DEBUG > 2 (or similar)
|
231
|
+
during development (until version 1.0) DEBUG should be activated
|
232
|
+
by default,
|
233
|
+
people could experiment with it and experts could deactivate DEBUG
|
234
|
+
(bbg) cleaned old textline functions.
|
235
|
+
|
236
|
+
11/9
|
237
|
+
(js) have fixed two major bugs, gocr now works again (but only -m 56 works)
|
238
|
+
|
239
|
+
18/9
|
240
|
+
(js) pedantic compiler warnings removed
|
241
|
+
bbg: compiling using pam (netpbm, see 22/9) functions generate some warnings,
|
242
|
+
which are caused by pam.h and do not affect gocr.
|
243
|
+
(js) list_del() does not work proper in context_correction(), fixed
|
244
|
+
bbg: list_del return value should be checked always. I'm not sure what
|
245
|
+
behaviour you want, so I didn't add the checks.
|
246
|
+
(js) malloc_box() bug fixed (memcpy src-dest mismatch)
|
247
|
+
|
248
|
+
21/9
|
249
|
+
(js) pgm2asc.c L1954, 2nd scan removed, now much faster, but
|
250
|
+
handling of umlaut etc. is missing (similar to gluing function)
|
251
|
+
bbg: umlaut is detected. Are you sure it's missing?
|
252
|
+
(js) I am away until Sept 30th 2000
|
253
|
+
|
254
|
+
22/9
|
255
|
+
|bbg| pnm_readpnmrow() SIGSEGV's. Don't know why.
|
256
|
+
?js? (when does it happens? example file?)
|
257
|
+
bbg: any file, here. Does it work for you? Are you sure isn't the pam
|
258
|
+
functions?
|
259
|
+
(bbg) added new code to read pnm's using netpbm package (pam* functions). It
|
260
|
+
works, but the drawback is that only recent (August 2000) libraries have
|
261
|
+
these functions. Added test for pam.h in configure.
|
262
|
+
[bbg] moved example files to ~/tests/. Updated Makefile.in to reflect changes
|
263
|
+
and moved the pertinent stuff to tests/Makefile. I don't have experience
|
264
|
+
with autoconf, but I think I did it right. :)
|
265
|
+
(bbg) fixed tests for unistd.h, which were missing.
|
266
|
+
|bbg| How to change gocr.tcl splitted windows proportion? It'd be nice to be
|
267
|
+
able to have a larger output area.
|
268
|
+
|bbg| gotta fix make.bat. There's a make for DOS, however; should we delete
|
269
|
+
make.bat?
|
270
|
+
(bbg) wrote INSTALL. Moved (no changes) history from README.txt to HISTORY.
|
271
|
+
|bbg| review README.txt. Create a TODO file, BUGS, etc.
|
272
|
+
:done
|
273
|
+
|
274
|
+
23/9
|
275
|
+
?bbg? database.c::ocr_db(), is any use for box3?
|
276
|
+
(bbg) added "Elapsed time".
|
277
|
+
(bbg) minor fixes.
|
278
|
+
|
279
|
+
24/9
|
280
|
+
|bbg| remove_dust() broken? It's not being used currently, since it's the last
|
281
|
+
piece of code using old list functions, and if it's updated, ocr1.c returns
|
282
|
+
a bunch of "#hmm, something was going wrong". So, the problem may be in
|
283
|
+
ocr1.c. I wrote the patch for remove_dust(), it's in #ifdefs.
|
284
|
+
:done
|
285
|
+
(bbg) patched rest of remove.c to with new list functions.
|
286
|
+
[bbg] remove_pictures() loop is weird. I followed what was there, but it should
|
287
|
+
be checked.
|
288
|
+
|
289
|
+
1/10
|
290
|
+
(bbg) for_each_data now checks the return value of list_higher_level().
|
291
|
+
(bbg) moved some functions to pixel.c
|
292
|
+
(bbg) some cleanup
|
293
|
+
|
294
|
+
3/10
|
295
|
+
(js) minor changes in Makefiles, add_line_infos() improved
|
296
|
+
|
297
|
+
6/10
|
298
|
+
(bbg) fixed bug when inserting a node before header, in list_ins().
|
299
|
+
(bbg) fixed bug that made for_each_data use list->header twice: l->fix wasn't
|
300
|
+
properly initialized.
|
301
|
+
(bbg) added list_sort(). Runned some tests, seems to be OK.
|
302
|
+
|
303
|
+
7/10
|
304
|
+
(bbg) updated list_sort() to a faster version. Runned tests.
|
305
|
+
(bbg) some minor cosmetic fixes
|
306
|
+
|bbg| amiga.h: is it really needed, can someone test it?
|
307
|
+
|bbg| As soon as remove_dust is fixed, the old list code can be deleted, which
|
308
|
+
would be nice. So, Joerg, can you please fix it? Thanks.
|
309
|
+
[js] Have I fixed it?
|
310
|
+
:done
|
311
|
+
|
312
|
+
9/10
|
313
|
+
(mg) moved gocr.tcl and create_db to new bin folder
|
314
|
+
(mg) cleaned up Makefile.in (some subdirs not included yet)
|
315
|
+
(mg) created new sub-folder lib
|
316
|
+
(mg) created new sub-folder include
|
317
|
+
[mg] installation for src is done very rudimentary
|
318
|
+
|
319
|
+
13/10
|
320
|
+
(bbg) split README.txt in BUGS, TODO and CREDITS. Joerg: Please write an AUTHORS
|
321
|
+
file.
|
322
|
+
(bbg) renamed README.txt to README.
|
323
|
+
(bbg) added list_empty(). Fixed list_higher_level to avoid empty lists. BTW: I
|
324
|
+
think that passing an empty list (l->header==NULL) may blow some of the
|
325
|
+
list functions.
|
326
|
+
|
327
|
+
16/10
|
328
|
+
(bbg) added AUTHORS.
|
329
|
+
|
330
|
+
22/10
|
331
|
+
(js) minor changes, glue_broken_chars() improved, ocr0 updated
|
332
|
+
?js? list_del() seems not to work in nested for_each_element()-loops
|
333
|
+
[js] remove_dust fixed?
|
334
|
+
:done
|
335
|
+
|
336
|
+
23/10
|
337
|
+
(bbg) rewrote list_del, using a new kind of fix. It will work as long as the
|
338
|
+
data is not freed by the user. A solution to fix this is to pass a pointer
|
339
|
+
to a function that will free the data.
|
340
|
+
|
341
|
+
25/10
|
342
|
+
(js) glue_broken_chars() recognition of "=" fixed, some other bugs fixed
|
343
|
+
(js) some improvements for recognition (ocr0n.c,ocr0.c)
|
344
|
+
|
345
|
+
27/10
|
346
|
+
(js) further improvements for better recognition results, polish.tex added
|
347
|
+
|
348
|
+
28/10
|
349
|
+
(bbg) changed free_boxtree() to new code
|
350
|
+
|bbg| have to fix the reast of the old box code
|
351
|
+
:done
|
352
|
+
|
353
|
+
4/11
|
354
|
+
[bbg] one of the frees of the new free_boxtree code sigsevs. I dunno why.
|
355
|
+
(js) boxlist->element->p is a pointer to existing whole pixmap, do not free this!
|
356
|
+
[bbg] I commented the following lines of pgmasc.c: 1430,43,55,67,81,95, since
|
357
|
+
they seem to be unnecessary.
|
358
|
+
(js) hmm: they are not needed for list_ins, but could be usefull for
|
359
|
+
a engine which looks for surrounding boxes. Do you know what I mean?
|
360
|
+
It was the last step of the conversion to the
|
361
|
+
new list routines. *uf*.
|
362
|
+
(bbg) ALL OLD CODE ROUTINES ARE DEPRECATED NOW. Mission successful, waiting for
|
363
|
+
permission to delete. :)
|
364
|
+
(js) permission granted
|
365
|
+
(bbg) Just to reassure, I tested gocr today and it's 100%
|
366
|
+
[bbg] change sort_boxes to a call to list_sort. sort_box_func should be
|
367
|
+
reviewed
|
368
|
+
(js) looks ok to me.
|
369
|
+
or tini_list(){
|
370
|
+
(js) ???
|
371
|
+
?bbg? ini_list(), exclude() & getresult(): should they be deleted?
|
372
|
+
(js) not found :(
|
373
|
+
I'm working
|
374
|
+
on a probability based engine, using neural networks.
|
375
|
+
|
376
|
+
6/11
|
377
|
+
(js) get Segmentation fault, => fixed
|
378
|
+
|
379
|
+
14/11
|
380
|
+
(bbg) deleted old list code.
|
381
|
+
(bbg) moved all detect* functions to detect.c
|
382
|
+
(bbg) movde lines functions to lines.c
|
383
|
+
|
384
|
+
22/11
|
385
|
+
(bbg) reviewed frame_nn(), mark_nn(), num_hole(), num_obj(). Some other minor
|
386
|
+
revisions.
|
387
|
+
(bbg) added outbounds() macro in gocr.h. It should be used from now on.
|
388
|
+
|
389
|
+
24/11
|
390
|
+
(js) some patches by J.R.V. Zandt added
|
391
|
+
?js? have still problems detecting pnm-libs via autoconf/configure
|
392
|
+
|
393
|
+
25/11
|
394
|
+
(bbg) added HTML support for all ISO8859-1 characters in unicode.
|
395
|
+
|
396
|
+
27/11
|
397
|
+
(bbg) some fixes in unicode.*
|
398
|
+
|bbg| whatletter needs a serious revision.
|
399
|
+
|
400
|
+
30/11
|
401
|
+
[js] split ocr0.c (compiles faster now), gcc 2.95.1 "bug" removed?
|
402
|
+
|
403
|
+
10/12
|
404
|
+
[bbg] Unicode is now supported. Some tests should be made, specially testing
|
405
|
+
UNKNOWN/PICTURE and >0xFF characters.
|
406
|
+
|
407
|
+
17/12
|
408
|
+
[js] pamlib,netlib,pnmlib detection (configure.in) changed
|
409
|
+
|
410
|
+
21/12
|
411
|
+
[jrv] pgm2asc changes:
|
412
|
+
context_correction() BUGFIX: test whether
|
413
|
+
previous(previous(current)) exists, before trying to dereferencing the pointer.
|
414
|
+
follow_path() introduced: follow a path, recording transitions
|
415
|
+
between dark and light.
|
416
|
+
xrealloc() introduced: safe memory allocation
|
417
|
+
loop() optimization: move direction test outside loop, simplify loop test
|
418
|
+
measure_pitch() introduced: detect monospaced font and measure the pitch
|
419
|
+
pgm2asc(): if font is monospaced, set spc per measured character spacing.
|
420
|
+
A few wording fixes.
|
421
|
+
|
422
|
+
05/01
|
423
|
+
(js) some fixes in glue_broken_chars results in good ";" and "!" detection
|
424
|
+
engine updated (examples/font1.pbm should work perfect)
|
425
|
+
|
426
|
+
19/02
|
427
|
+
(js) "make dist" now automaticly makes packaging (gocr-x.y.z.tgz)
|
428
|
+
does the Makefile in api working (especially make clean/proper)?
|
429
|
+
"make install" should work too
|
430
|
+
bbg: API makefiles work, but there's no make proper (use distclean instead)
|
431
|
+
I'd appreciate if someone could test the configure and libpnm. install is
|
432
|
+
not tested yet.
|
433
|
+
|
434
|
+
19/04
|
435
|
+
[js] USE_UNICODE defined as default in gocr.h (test it), some fixes to get
|
436
|
+
-f TeX, -f HTML running, fixed bug in lines.c (unterminated string)
|
437
|
+
measure_pitch extended to 12<width<150 (see example)
|
438
|
+
|
439
|
+
15/05
|
440
|
+
[js] list.c line 225+226 realloc( .., (l->level+2)..) correct? (S.Niemz bug)
|
441
|
+
|
442
|
+
30/07
|
443
|
+
?js? readpnm if USE_libpnm does not the job of old readpgm (for pbm-files)
|
444
|
+
|
445
|
+
22/08
|
446
|
+
(js) gcc -Wall -pedantic warnings fixed, ocr0.c wchar_t used by default
|
447
|
+
we should switch to wchar_t, its more flexible and ANSI (?)
|
448
|
+
and the huge number of "#ifdef USE_UNICODE" statements are looking bad
|
449
|
+
?js? can someone compile test on a machine without wchar.h? (FREEBSD?)
|
450
|
+
|
451
|
+
25/08
|
452
|
+
?js? I got following warning by gcc 2.95.3 20010315 (-Wall -pedantic):
|
453
|
+
lines.c: In function 'store_boxtree_lines':
|
454
|
+
lines.c:136: warning: implicit declaration of function 'wcsdup'
|
455
|
+
but I included <wchar.h>. Does anybody understand this???
|
456
|
+
hmmm ... Is it because of not ANSI (but GNU) extension?
|
457
|
+
What should we do with non-standart C-functions?
|
458
|
+
May be therefore I got the complains from FREEBSD users?
|
459
|
+
|
460
|
+
30/08
|
461
|
+
(js) pgm2asc.c, output.c simplified, improvement of char-devision
|
462
|
+
|
463
|
+
08/02/2002
|
464
|
+
?js? all possible SIGSEGVs in list.c fixed
|
465
|
+
|
466
|
+
15/02/2002
|
467
|
+
[js] ocr0.c will use setac() in future manipulating struct box - tac,wac
|
468
|
+
and c, if chars are very similar this will make context correction more
|
469
|
+
easyly, filtering will be more easily too (not fully implemented)
|
470
|
+
|
471
|
+
25/02/2002
|
472
|
+
[js] box->obj added for storing more than one char
|
473
|
+
|
474
|
+
02/06/2002
|
475
|
+
(jb) added special encodings for '&', '<', '>' to HTML decoder
|
476
|
+
|
477
|
+
05/06/2002
|
478
|
+
[jb] job_t introduced (same patch as sent to the mailing list)
|
479
|
+
Only local variables (configuration and pixmap) of main() are
|
480
|
+
moved inside job_t yet.
|
481
|
+
[jb] boxlist and linelist converted to job_t
|
482
|
+
[jb] Temorary introduction of global variable JOB (of type job_t)
|
483
|
+
This variable will be removed, while all functions are converted to
|
484
|
+
receive either an job_t pointer or the needed values.
|
485
|
+
[jb] n_run, env, db_path and ppo converted to job_t
|
486
|
+
[jb] converted dblist
|
487
|
+
[jb] renamed init_job and free_job to job_free and job_init
|
488
|
+
[jb] converted nearly all global variables (except warn and debug) to
|
489
|
+
job_t. Used JOB as new temporaryr global variable.
|
490
|
+
Overview of the renaming (some old variables are combined to a new one):
|
491
|
+
|
492
|
+
OLD VAR NAMES NEW VAR NAME
|
493
|
+
* main():inam JOB->src.fname
|
494
|
+
* main():p JOB->src.p
|
495
|
+
env.p
|
496
|
+
* main():init JOB->tmp.init_time
|
497
|
+
* ppo JOB->tmp.ppo
|
498
|
+
* n_run JOB->tmp.n_run
|
499
|
+
* dblist JOB->tmp.dblist
|
500
|
+
* boxlist JOB->res.boxlist
|
501
|
+
* linelist JOB->res.linelist
|
502
|
+
* lines JOB->res.lines
|
503
|
+
* env.avX JOB->res.avX
|
504
|
+
* env.avY JOB->res.avY
|
505
|
+
* env.sumX JOB->res.sumX
|
506
|
+
* env.sumY JOB->res.sumY
|
507
|
+
* env.numC JOB->res.numC
|
508
|
+
* main():cs JOB->cfg.cs
|
509
|
+
env.cs
|
510
|
+
* main():spc JOB->cfg.spc
|
511
|
+
* main():mo JOB->cfg.mode
|
512
|
+
env.mode
|
513
|
+
* main():dust_size JOB->cfg.dust_size
|
514
|
+
* main():numo JOB->cfg.only_numbers
|
515
|
+
only_numbers
|
516
|
+
* main():verbose JOB->cfg.verbose
|
517
|
+
env.vvv
|
518
|
+
* main():out_format JOB->cfg.out_format
|
519
|
+
* main():lc JOB->cfg.lc
|
520
|
+
* env.db_path JOB->cfg.db_path
|
521
|
+
|
522
|
+
[jb] introduced list_and_data_free
|
523
|
+
|
524
|
+
|jb| get rid of JOB.
|
525
|
+
|jb| decide on last global variables "warn" and "debug"
|
526
|
+
js: its thought for debugging, we should use MACROS WARN or DEBUG
|
527
|
+
|jb| eliminate static buffers inside fucntions.
|
528
|
+
|
529
|
+
30/06/2002
|
530
|
+
(js) gocr.h: struct box: modifier now wchar_t
|
531
|
+
mark things, which need changes with "ToDo:" directly in the sources,
|
532
|
+
so that we can grep for it and see that there are planed changes
|
533
|
+
|
534
|
+
05/01/2003
|
535
|
+
(js) ocr0.c: engine splitted in groups of characters (mostly pairs)
|
536
|
+
num_hole called once for every char, result is stored in a table
|
537
|
+
?js? cvs ci jocr does not work since 2003? (it tries to update jocr/CVS)
|
538
|
+
have cvs-1.11.1p1
|